conftrace_

saddle point

95 papers

Explore in graph

Also known as

SP

Co-occurring keywords

non-convex optimization (547) stochastic gradient descent (1091) gradient descent (1144) nonconvex optimization (316) second-order stationary point (31) stochastic optimization (1060) convex optimization (1321) local minimum (61) critical point (24) gradient flow (142)

Papers

Convergence of Fast Policy Iteration in Markov Games and Robust MDPs AAAI 2026
Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles JMLR 2025
Stabilizing Sharpness-Aware Minimization Through A Simple Renormalization Strategy JMLR 2025
Efficiently Escaping Saddle Points in Bilevel Optimization JMLR 2025
Escaping Saddle Point Efficiently in Minimax and Bilevel Optimizations IJCAI 2025
Towards Understanding Gradient Flow Dynamics of Homogeneous Neural Networks Beyond the Origin JMLR 2025
Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression AISTATS 2024
Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry NIPS 2024
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks? NIPS 2024
High Probability and Risk-Averse Guarantees for a Stochastic Accelerated Primal-Dual Method JMLR 2024
Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses AISTATS 2024
The Loss Landscape of Deep Linear Neural Networks: a Second-order Analysis JMLR 2024
Competitive Gradient Optimization ICML 2023
An SDE for Modeling SAM: Theory and Insights ICML 2023
Riemannian stochastic optimization methods avoid strict saddle points NIPS 2023
Linear Regularizers Enforce the Strict Saddle Property AAAI 2023
Finding Local Minima Efficiently in Decentralized Optimization NIPS 2023
Online Saddle Point Tracking with Decision-Dependent Data L4DC 2023
HOUDINI: Escaping from Moderately Constrained Saddles IJCAI 2023
Efficient Hyper-parameter Optimization with Cubic Regularization NIPS 2023
Randomized Primal-Dual Methods with Adaptive Step Sizes AISTATS 2023
Saddle-to-Saddle Dynamics in Diagonal Linear Networks NIPS 2023
Escaping saddle points in zeroth-order optimization: the power of two-point estimators ICML 2023
Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs NIPS 2023
Power-Law Escape Rate of SGD ICML 2022